Training in progress, step 20, checkpoint

last-checkpoint/adapter_config.json

@@ -20,8 +20,7 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
-    "word_embeddings"
+    "query_key_value"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a36d600cb075593139b01f4d1f27775faa37b77eacaf43dd2393c880d628c4e
-size 12803224
+oid sha256:7cee5316db6e08bda593292c7431684b3dc73870ce8a54a0c3a013496aab2e9e
+size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e8d270f06b401efc87dfffdef9e44213731951a0be1e0698c2b5564562d00f9
-size 6472698
+oid sha256:7cb629127bd34551a67b577b0df727a8ad10f3cfd7c565e8d20049369b722415
+size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1300bb8ffdcaac24edcc93c280d512ef74e120d1952b429e8e1905153ce6021f
+oid sha256:2459c05c4cdd21f5e13527642f659d90d83beb16d5e41ba0b50749a967c819c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79897bc37c77685183e620e5ff5489b797fe11af9975c9cb5639933de38b4cff
+oid sha256:d0351811b292a925d9e90fecda402ef74b5027ecf82c420e29489a6a985de561
 size 1064

last-checkpoint/tokenizer_config.json

@@ -40,7 +40,9 @@
   "max_length": 2048,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
+  "padding": true,
   "padding_side": "right",
   "tokenizer_class": "BloomTokenizer",
+  "truncation": true,
   "unk_token": "<unk>"
 }

last-checkpoint/trainer_state.json

@@ -1,33 +1,19 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00018678060283439565,
+  "epoch": 1.5565050236199638e-05,
   "eval_steps": 500,
-  "global_step": 60,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0,
-      "grad_norm": 75.3083267211914,
+      "grad_norm": 4.044270038604736,
       "learning_rate": 1.6666666666666667e-06,
-      "loss": 3.6651,
+      "loss": 3.7393,
       "step": 20
-    },
-    {
-      "epoch": 0.0,
-      "grad_norm": 90.37364196777344,
-      "learning_rate": 3.3333333333333333e-06,
-      "loss": 3.7271,
-      "step": 40
-    },
-    {
-      "epoch": 0.0,
-      "grad_norm": 47.56499481201172,
-      "learning_rate": 5e-06,
-      "loss": 3.5867,
-      "step": 60
     }
   ],
   "logging_steps": 20,
@@ -35,7 +21,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 139848644812800.0,
+  "total_flos": 6641137152000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f81e09372397f7e5aa06ad532b71524705df27d8d386bc119142c8b4c15cf6b1
+oid sha256:67d9137f50a05785e0ffd11f3ee590825d65f6fa4ba75fb2184bf1dc9266179b
 size 4984